Loss is about 2.x, but mAP is not good, only about 66.x%.

[XiangqianMa]

I have tried many training tricks, such as different batch_size, different learning rate. But, almost each loss is 2.x. I checked other issues, their mAP are 7x.x%, but mine is 66.x%. So does anyone encounter such problem?

[yinyuhangi]

My loss is also 2.x, mAP is 68.3%

[rechealzrq]

Have you solved your problem?

[ChenT1994]

I have tried many training tricks, such as different batch_size, different learning rate. But, almost each loss is 2.x. I checked other issues, their mAP are 7x.x%, but mine is 66.x%. So does anyone encounter such problem?

I have tried many training tricks, such as different batch_size, different learning rate. But, almost each loss is 2.x. I checked other issues, their mAP are 7x.x%, but mine is 66.x%. So does anyone encounter such problem?

I have tried many training tricks, such as different batch_size, different learning rate. But, almost each loss is 2.x. I checked other issues, their mAP are 7x.x%, but mine is 66.x%. So does anyone encounter such problem?

I have the same problem,Did you find the reason?

[Bobby2090]

I have tried many training tricks, such as different batch_size, different learning rate. But, almost each loss is 2.x. I checked other issues, their mAP are 7x.x%, but mine is 66.x%. So does anyone encounter such problem?

我最近也遇到了这个问题，你解决了吗？求指导，谢谢